AGV monocular vision localization algorithm based on Gaussian saliency heuristic
Abstract To address the issues of poor detection accuracy and the large number of target detection model parameters in existing AGV monocular vision location detection algorithms, this paper presents an AGV vision location method based on Gaussian saliency heuristic. The proposed method introduces a...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-03-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13634-024-01112-8 |
| _version_ | 1797246903151230976 |
|---|---|
| author | Heng Fu Yakai Hu Shuhua Zhao Jianxin Zhu Benxue Liu Zhen Yang |
| author_facet | Heng Fu Yakai Hu Shuhua Zhao Jianxin Zhu Benxue Liu Zhen Yang |
| author_sort | Heng Fu |
| collection | DOAJ |
| description | Abstract To address the issues of poor detection accuracy and the large number of target detection model parameters in existing AGV monocular vision location detection algorithms, this paper presents an AGV vision location method based on Gaussian saliency heuristic. The proposed method introduces a fast and accurate AGV visual detection network called GAGV-net. In the GAGV-net network, a Gaussian saliency feature extraction module is designed to enhance the network’s feature extraction capability, thereby reducing the required output for model fitting. To improve the accuracy of target detection, a joint multi-scale classification and detection task header are designed at the stage of target frame regression to classification. This header utilizes target features of different scales, thereby enhancing the accuracy of target detection. Experimental results demonstrate a 12% improvement in detection accuracy and a 27.38 FPS increase in detection speed compared to existing detection methods. Moreover, the proposed detection network significantly reduces the model’s size, enhances the network model’s deployability on AGVs, and greatly improves detection accuracy. |
| first_indexed | 2024-04-24T19:50:11Z |
| format | Article |
| id | doaj.art-03ee945bb18747fea769d7c1869b9d86 |
| institution | Directory Open Access Journal |
| issn | 1687-6180 |
| language | English |
| last_indexed | 2024-04-24T19:50:11Z |
| publishDate | 2024-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-03ee945bb18747fea769d7c1869b9d862024-03-24T12:37:12ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802024-03-012024111510.1186/s13634-024-01112-8AGV monocular vision localization algorithm based on Gaussian saliency heuristicHeng Fu0Yakai Hu1Shuhua Zhao2Jianxin Zhu3Benxue Liu4Zhen Yang5Anyang Cigarette Factory of Henan China Tobacco Industry Co., LtdAnyang Cigarette Factory of Henan China Tobacco Industry Co., LtdAnyang Cigarette Factory of Henan China Tobacco Industry Co., LtdAnyang Cigarette Factory of Henan China Tobacco Industry Co., LtdZhengzhou UniversityZhengzhou UniversityAbstract To address the issues of poor detection accuracy and the large number of target detection model parameters in existing AGV monocular vision location detection algorithms, this paper presents an AGV vision location method based on Gaussian saliency heuristic. The proposed method introduces a fast and accurate AGV visual detection network called GAGV-net. In the GAGV-net network, a Gaussian saliency feature extraction module is designed to enhance the network’s feature extraction capability, thereby reducing the required output for model fitting. To improve the accuracy of target detection, a joint multi-scale classification and detection task header are designed at the stage of target frame regression to classification. This header utilizes target features of different scales, thereby enhancing the accuracy of target detection. Experimental results demonstrate a 12% improvement in detection accuracy and a 27.38 FPS increase in detection speed compared to existing detection methods. Moreover, the proposed detection network significantly reduces the model’s size, enhances the network model’s deployability on AGVs, and greatly improves detection accuracy.https://doi.org/10.1186/s13634-024-01112-8AGV monocular vision locationGaussian saliency enhancementGAGV-net |
| spellingShingle | Heng Fu Yakai Hu Shuhua Zhao Jianxin Zhu Benxue Liu Zhen Yang AGV monocular vision localization algorithm based on Gaussian saliency heuristic EURASIP Journal on Advances in Signal Processing AGV monocular vision location Gaussian saliency enhancement GAGV-net |
| title | AGV monocular vision localization algorithm based on Gaussian saliency heuristic |
| title_full | AGV monocular vision localization algorithm based on Gaussian saliency heuristic |
| title_fullStr | AGV monocular vision localization algorithm based on Gaussian saliency heuristic |
| title_full_unstemmed | AGV monocular vision localization algorithm based on Gaussian saliency heuristic |
| title_short | AGV monocular vision localization algorithm based on Gaussian saliency heuristic |
| title_sort | agv monocular vision localization algorithm based on gaussian saliency heuristic |
| topic | AGV monocular vision location Gaussian saliency enhancement GAGV-net |
| url | https://doi.org/10.1186/s13634-024-01112-8 |
| work_keys_str_mv | AT hengfu agvmonocularvisionlocalizationalgorithmbasedongaussiansaliencyheuristic AT yakaihu agvmonocularvisionlocalizationalgorithmbasedongaussiansaliencyheuristic AT shuhuazhao agvmonocularvisionlocalizationalgorithmbasedongaussiansaliencyheuristic AT jianxinzhu agvmonocularvisionlocalizationalgorithmbasedongaussiansaliencyheuristic AT benxueliu agvmonocularvisionlocalizationalgorithmbasedongaussiansaliencyheuristic AT zhenyang agvmonocularvisionlocalizationalgorithmbasedongaussiansaliencyheuristic |